Instructions to use Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF",
	filename="Qwen3.5-9B-DeepSeek-V4-Flash-MTP-BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF with Ollama:
```
ollama run hf.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M
```

Unsloth Studio

How to use Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open /spaces/unsloth/studio in your browser
# Search for Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF to start chatting

How to use Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M
```

Lemonade

How to use Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF-Q4_K_M

List all available models

lemonade list

Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF

Source model: Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash MTP source fallback: unsloth/Qwen3.5-9B

Uploaded GGUF variants:

Qwen3.5-9B-DeepSeek-V4-Flash-MTP-Q2_K.gguf
Qwen3.5-9B-DeepSeek-V4-Flash-MTP-Q3_K_S.gguf
Qwen3.5-9B-DeepSeek-V4-Flash-MTP-Q3_K_M.gguf
Qwen3.5-9B-DeepSeek-V4-Flash-MTP-Q3_K_L.gguf
Qwen3.5-9B-DeepSeek-V4-Flash-MTP-IQ4_XS.gguf
Qwen3.5-9B-DeepSeek-V4-Flash-MTP-Q4_K_S.gguf
Qwen3.5-9B-DeepSeek-V4-Flash-MTP-Q4_K_M.gguf
Qwen3.5-9B-DeepSeek-V4-Flash-MTP-Q5_K_S.gguf
Qwen3.5-9B-DeepSeek-V4-Flash-MTP-Q5_K_M.gguf
Qwen3.5-9B-DeepSeek-V4-Flash-MTP-Q6_K.gguf
Qwen3.5-9B-DeepSeek-V4-Flash-MTP-Q8_0.gguf
Qwen3.5-9B-DeepSeek-V4-Flash-MTP-BF16.gguf

The conversion pipeline first verifies whether the source HF model already contains MTP tensors. If not, it extracts the MTP tensors from the matching unsloth base model and injects them into the safetensors index before GGUF conversion.